Simulation-based methods are (currently only) supported.

get_p_value(x, obs_stat, direction)

get_pvalue(x, obs_stat, direction)

Arguments

x

Data frame of calculated statistics as returned by generate()

obs_stat

A numeric value or a 1x1 data frame (as extreme or more extreme than this).

direction

A character string. Options are "less", "greater", or "two_sided". Can also use "left", "right", or "both".

Value

A 1x1 tibble with value between 0 and 1.

Aliases

get_pvalue() is an alias of get_p_value(). p_value is a deprecated alias of get_p_value().

Examples

# Prepare the dataset mtcars_df <- mtcars %>% dplyr::mutate(am = factor(am)) # Calculate the difference in means in the dataset d_hat <- mtcars_df %>% specify(mpg ~ am) %>% calculate(stat = "diff in means", order = c("1", "0")) # Same calculation on 100 permutation replicates null_distn <- mtcars_df %>% specify(mpg ~ am) %>% hypothesize(null = "independence") %>% generate(reps = 100) %>% calculate(stat = "diff in means", order = c("1", "0"))
#> Setting `type = "permute"` in `generate()`.
# What proportion of replicates had a difference # in means more extreme than in the dataset? null_distn %>% get_p_value(obs_stat = d_hat, direction = "right")
#> # A tibble: 1 x 1 #> p_value #> <dbl> #> 1 0